{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4OSD7ZWYISQNT7LXT6PZA7K5FI","short_pith_number":"pith:4OSD7ZWY","canonical_record":{"source":{"id":"2506.14824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:50:50Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c434315af673eac3ba531422952bba37ed2bc53d22f40cd80400a91571f9fc4d","abstract_canon_sha256":"384edf58580270f1b2406ff7c6120b83e5f58f2a950904af86177154dd310b71"},"schema_version":"1.0"},"canonical_sha256":"e3a43fe6d844a0d9fd779f9f907d5d2a1292aa1398ccb45a7398c6ff58e6bdfc","source":{"kind":"arxiv","id":"2506.14824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14824","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14824v1","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14824","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"4OSD7ZWYISQN","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"4OSD7ZWYISQNT7LX","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"4OSD7ZWY","created_at":"2026-07-05T11:23:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4OSD7ZWYISQNT7LXT6PZA7K5FI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:50:50Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c434315af673eac3ba531422952bba37ed2bc53d22f40cd80400a91571f9fc4d","abstract_canon_sha256":"384edf58580270f1b2406ff7c6120b83e5f58f2a950904af86177154dd310b71"},"schema_version":"1.0"},"canonical_sha256":"e3a43fe6d844a0d9fd779f9f907d5d2a1292aa1398ccb45a7398c6ff58e6bdfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:32.261140Z","signature_b64":"WVdJnAOTvEfk3oORZsQP1hhEkWqQ2MlAdUN0UhaOUbZmOeqPIBp5ULGxMkcLwn2FdhE1zwM9txUffXhye7UkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a43fe6d844a0d9fd779f9f907d5d2a1292aa1398ccb45a7398c6ff58e6bdfc","last_reissued_at":"2026-07-05T11:23:32.260685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:32.260685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14824","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8f9Oeu0gUNMVqR4ivpFNWW4vp9PoEzlq2UPj3f1pozTYH+Reuhe5JvgwkrnB23TSNP1YaOqepBlR3M74j9TAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:08:49.078512Z"},"content_sha256":"414bc1ac9f3bd2a45a5ebb7d7de8b7c7e27ac53bf129c7d81b8f26409bedfa8c","schema_version":"1.0","event_id":"sha256:414bc1ac9f3bd2a45a5ebb7d7de8b7c7e27ac53bf129c7d81b8f26409bedfa8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4OSD7ZWYISQNT7LXT6PZA7K5FI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.LG","authors_text":"Haokun Chen, Hewei Gao, Volker Tresp, Weiguo Li, Yao Zhang, Yunpu Ma","submitted_at":"2025-06-12T17:50:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in tasks like multimodal reasoning and cross-modal retrieval but face deployment challenges in real-world scenarios due to distributed multimodal data and strict privacy requirements. Federated Learning (FL) offers a solution by enabling collaborative model training without centralizing data. However, realizing FL for MLLMs presents significant challenges, including high computational demands, limited client capacity, substantial communication costs, and heterogeneous client data. Existing FL methods assume client-side deployment of full models, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14824","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.14824/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pA24JMEUI+Rye8HMz9Mh5Co+HPlXzzUaQSifU/w7KTEu2B+rYboHEcWZNsLfKFFY+PqXbYMa9xHnwR9Ye7ZTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:08:49.079045Z"},"content_sha256":"758a3a05dc1ce568e45ddcc931094dbf8396a4c406f11d6550eb00131ecc04ab","schema_version":"1.0","event_id":"sha256:758a3a05dc1ce568e45ddcc931094dbf8396a4c406f11d6550eb00131ecc04ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/bundle.json","state_url":"https://pith.science/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T19:08:49Z","links":{"resolver":"https://pith.science/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI","bundle":"https://pith.science/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/bundle.json","state":"https://pith.science/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OSD7ZWYISQNT7LXT6PZA7K5FI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4OSD7ZWYISQNT7LXT6PZA7K5FI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"384edf58580270f1b2406ff7c6120b83e5f58f2a950904af86177154dd310b71","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:50:50Z","title_canon_sha256":"c434315af673eac3ba531422952bba37ed2bc53d22f40cd80400a91571f9fc4d"},"schema_version":"1.0","source":{"id":"2506.14824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14824","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14824v1","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14824","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"4OSD7ZWYISQN","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"4OSD7ZWYISQNT7LX","created_at":"2026-07-05T11:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"4OSD7ZWY","created_at":"2026-07-05T11:23:32Z"}],"graph_snapshots":[{"event_id":"sha256:758a3a05dc1ce568e45ddcc931094dbf8396a4c406f11d6550eb00131ecc04ab","target":"graph","created_at":"2026-07-05T11:23:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.14824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in tasks like multimodal reasoning and cross-modal retrieval but face deployment challenges in real-world scenarios due to distributed multimodal data and strict privacy requirements. Federated Learning (FL) offers a solution by enabling collaborative model training without centralizing data. However, realizing FL for MLLMs presents significant challenges, including high computational demands, limited client capacity, substantial communication costs, and heterogeneous client data. Existing FL methods assume client-side deployment of full models, a","authors_text":"Haokun Chen, Hewei Gao, Volker Tresp, Weiguo Li, Yao Zhang, Yunpu Ma","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:50:50Z","title":"FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14824","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:414bc1ac9f3bd2a45a5ebb7d7de8b7c7e27ac53bf129c7d81b8f26409bedfa8c","target":"record","created_at":"2026-07-05T11:23:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"384edf58580270f1b2406ff7c6120b83e5f58f2a950904af86177154dd310b71","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:50:50Z","title_canon_sha256":"c434315af673eac3ba531422952bba37ed2bc53d22f40cd80400a91571f9fc4d"},"schema_version":"1.0","source":{"id":"2506.14824","kind":"arxiv","version":1}},"canonical_sha256":"e3a43fe6d844a0d9fd779f9f907d5d2a1292aa1398ccb45a7398c6ff58e6bdfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3a43fe6d844a0d9fd779f9f907d5d2a1292aa1398ccb45a7398c6ff58e6bdfc","first_computed_at":"2026-07-05T11:23:32.260685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:32.260685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVdJnAOTvEfk3oORZsQP1hhEkWqQ2MlAdUN0UhaOUbZmOeqPIBp5ULGxMkcLwn2FdhE1zwM9txUffXhye7UkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:32.261140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:414bc1ac9f3bd2a45a5ebb7d7de8b7c7e27ac53bf129c7d81b8f26409bedfa8c","sha256:758a3a05dc1ce568e45ddcc931094dbf8396a4c406f11d6550eb00131ecc04ab"],"state_sha256":"991de945df9fed3e24c89c9903a82b86bdc8148df6d86660c69e60d8de970fa9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ahmg3rpU4FKu6uwbvIXFRJfCkcowcFgIBDjNN4AFFtNCBHL1XJjCcefT2nPK66tVqGb1GZnPTJNv9snbntxgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:08:49.082773Z","bundle_sha256":"ca99dd15d132242db998c4fdd649e68f463d6fbe19b8a5d0f329a49e1d34456f"}}